Skip to content
Local AI Wizard
Your machine
Theme

Smaug Agentic

Abacus AI · abacusai/Smaug-Agentic

Weights license: Publisher terms: Kimi K3 · code and components may use other terms

LiveBench · overall79.5 / 100#2 of 23 open models · 2026-06-25
Memory needed~2,100 GBQ4 weights + working room, before the machine's reserve
Parameters2,800 Bmanufacturer specification · 104B active
Context1,048,576 tokensPublished for this model

Quality

Quality · Overall

LiveBench 2026-06-25 · 0–100 · higher is better · this model outlined, #2 of 23

  • Color = publisher
  • Memory under review

Source: LiveBench 2026-06-25 · collected 2026-10-18 · open models without a score are not drawn (no score ≠ 0)

No result in LMArena 2026-10-22 Not in LMArena 2026-10-22

LiveBench categories

This model's mean per category · 0–100

90.3ReasoningReasoning82.5CodingCoding64.6Agentic CodingAgentic Coding83.9MathematicsMathematics79.9Data AnalysisData Analysis84.4LanguageLanguage71.0IFIF

Source: LiveBench 2026-06-25 · collected 2026-10-18 · open models without a score are not drawn (no score ≠ 0)

Reported by the publisher

8 results · Abacus AI's model card · read 2026-10-25
GPQA Diamond
94.1
AA-LCR
75.7
DeepSWE
69.9
Terminal-Bench 2.1
86.5
SciCode
60.8
LiveBench (Agentic Coding)
64.6
AutomationBench
31.0
MMMU-Pro
81.0

Values as printed on the card, with the publisher's own settings (card section: 3. Evaluation Results); column “Smaug-Agentic (max)”. Not comparable across publishers and not used in any ranking. Model card

Quality × memory

Quality × memory

LiveBench 2026-06-25 overall vs. Q4 planning memory (log scale) · 19 open models

  • This model
  • Color = publisher
40608010081632641282565121,0242,0484,096Memory needed · Q4 · model only (GB, log)LiveBenchQwen3.8 MaxDeepSeek V4 Pro · 0813Smaug MiniSmaug Agentic

Memory = the model's own figure: parameters × 0.625 bytes + 20% working room, before any machine's reserve; with a chosen machine, the total there with its reserve (25% of memory, 2 to 8 GB; 2 GB per graphics card). An estimate, not measured VRAM. LiveBench 2026-06-25

Runs on

More memory than any profile in the catalog

Even the largest profile (8 × 80 GB, aggregated) is below this planning estimate. Multi-node setups are outside this catalog.

Smaug Agentic is a text model from Abacus AI with 2,800B parameters, 104B of them active per token (mixture of experts). It was released on September 10, 2026 and reads up to 1,048,576 tokens of context. Its Q4 weights plus working room come to about 2,100 GB, more than the fast memory of every reference machine. No GGUF or MLX file for it was collected from the Hub, so this page lists no file sizes or run commands. It scores 79.5 overall in LiveBench 2026-06-25.

On the reference machines

Smaug Agentic on the reference machines
Where Q4 sits
Mac mini M2 · 8 GB unifiedLarger than its memory~2,102 GBLarger than its memory
Mac mini M4 · 16 GB unifiedLarger than its memory~2,104 GBLarger than its memory
Mac mini M4 · 24 GB unifiedLarger than its memory~2,106 GBLarger than its memory
Mac mini M4 · 32 GB unifiedLarger than its memory~2,108 GBLarger than its memory
Mac mini M5 Pro · 64 GB unifiedLarger than its memory~2,108 GBLarger than its memory
Mac Studio M5 Max · 128 GB unifiedLarger than its memory~2,108 GBLarger than its memory
Mac Studio · M5 Ultra · 36-core CPU / 80-core GPU · 512 GB unifiedLarger than its memory~2,108 GBLarger than its memory
RTX 4060 · 8 GB VRAMLarger than its memory~2,102 GBLarger than its memory
RTX 3060 · 12 GB VRAMLarger than its memory~2,102 GBLarger than its memory
RTX 5080 · 16 GB VRAMLarger than its memory~2,102 GBLarger than its memory
RTX 4090 · 24 GB VRAMLarger than its memory~2,102 GBLarger than its memory
RTX 5090 · 32 GB VRAMLarger than its memory~2,102 GBLarger than its memory
DGX H100 · 8 × 80 GBLarger than its memory~2,116 GBLarger than its memory

No GGUF or MLX file was collected for this checkpoint, so the table has no file column; the Q4 figures are planning estimates from the parameter count, not measured runs.

Plan another quantization or context

Consider it for

Compare Smaug Agentic using its publisher card and the LiveBench 2026-06-25 snapshot. This is quality evidence, not local speed.

Check first

The Q4 weights plus working room come to about 2100 GB from 2,800B stated parameters, before the machine's reserve (Runs on adds it per machine). It is not a measured minimum; context, batch size, runtime and quantization change actual memory use.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

The memory needed above is the Q4 load before a machine's reserve. Formula: parameters × 0.625 bytes, plus 20% working allowance; each machine then adds its system reserve: 25% of unified or system memory, 2 to 8 GB, or 2 GB per GPU on dedicated cards. This is neither measured VRAM nor checkpoint download size.

Q4 planning estimate only. Check checkpoint format, runtime support, KV cache, context, batch size and offload before choosing hardware.

Documented ways to run it

The model card points to another page without a command of its own

Evidence level: Generic estimate only; no execution reproduced by this site.

Versions to download
— No GGUF or MLX file collected from the Hub for this checkpoint
Publisher sampling defaults
— No Hub file facts collected for this checkpoint
Chat template markers
— Chat template not read for this checkpoint
Before downloading
  1. Check the exact checkpoint and license linked here.
  2. Confirm a compatible runtime and precision or quantization for your platform.
  3. Allow for context, batch size and any extra media components beyond the weights.

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / version
abacusai/Smaug-Agentic
Task and modality
language and reasoning · text + image
Count and basis
2,800B · manufacturer specification · 104B active
Context
1,048,576 tokens published for this model
Architecture
MoE
Released
Abacus.AI Launches the Smaug Line of Open-Weight Models Optimized for Enterprise Agentic AI Use Cases (PR Newswire, dateline Sept. 10, 2026) · read 2026-10-10source
Runtime and precision
No local execution verified.
Commercial use
Allowed with conditions Model-as-a-service operators over USD 20M yearly revenue need an agreement; large products show "Kimi K3" · Kimi K3 license (moonshotai/Kimi-K3 LICENSE) · read 2026-10-18license text
Every stored field10 fields
Revision checked
3cfed21972e7db48b277a349137e09a44142ec6c
Architecture
KimiK3ForConditionalGeneration
Library
transformers
Hub task tag
image-text-to-text
Formats
safetensors
Repository created
2026-08-10creation is not the model's release
Repository updated
2026-09-09a commit is not a release date
Hub downloads (30 days) · likes
173 · 25this repository only · read 2026-10-25
Read from the Hub page
task, transformers class, task tags, license name, file formatsHub overview and file listing · read 2026-10-18
Catalog state
Hub inventory current

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Catalog reviewed: 2026-09-30. Benchmark release: 2026-06-25; snapshot collected: 2026-10-18.